© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49621
    Prev
    Next
    INDEX
    Explanations

    water proof

    np_acts-logits-general · gemini-2.5-flash-lite

    why is, brand management, Earl Grey

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    approximately
    0.47
    𝘂
    0.46
    organized
    0.45
    ventory
    0.45
    selected
    0.44
    ophthal
    0.43
    avg
    0.43
    organization
    0.42
    licking
    0.42
    roughly
    0.41
    POSITIVE LOGITS
     babel
    0.46
     MUI
    0.46
    值为
    0.45
     值
    0.44
     Babel
    0.43
     miał
    0.43
     benzyl
    0.42
     yi
    0.41
    رهای
    0.41
    TabBar
    0.41
    Activations Density 0.000%

    No Known Activations